Hugging Face's logo

shenayx
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
PyTorch
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
shenayx commited on
Commit
d5340fd
•
1 Parent(s): 92883c7

Training in progress, epoch 0

Browse files
Files changed (22) hide show
  1. .gitattributes +34 -35
  2. .gitignore +1 -0
  3. README.md +66 -0
  4. all_results.json +8 -0
  5. config.json +55 -0
  6. model.safetensors +3 -0
  7. preprocessor_config.json +42 -0
  8. pytorch_model.bin +3 -0
  9. runs/Nov09_01-44-16_588d19775fbb/1667958337.1126697/events.out.tfevents.1667958337.588d19775fbb.280.1 +3 -0
  10. runs/Nov09_01-44-16_588d19775fbb/events.out.tfevents.1667958337.588d19775fbb.280.0 +3 -0
  11. runs/Nov09_01-44-16_588d19775fbb/events.out.tfevents.1667958570.588d19775fbb.280.2 +3 -0
  12. runs/Nov10_07-25-30_8182e899e964/1668065304.7947109/events.out.tfevents.1668065304.8182e899e964.107.1 +3 -0
  13. runs/Nov10_07-25-30_8182e899e964/events.out.tfevents.1668065304.8182e899e964.107.0 +3 -0
  14. runs/Nov10_07-39-57_8182e899e964/1668066010.4314957/events.out.tfevents.1668066010.8182e899e964.742.1 +3 -0
  15. runs/Nov10_07-39-57_8182e899e964/events.out.tfevents.1668066010.8182e899e964.742.0 +3 -0
  16. runs/Nov10_07-39-57_8182e899e964/events.out.tfevents.1668066300.8182e899e964.742.2 +3 -0
  17. runs/Nov10_08-33-15_c4cf3c5cebad/1668069370.6992447/events.out.tfevents.1668069370.c4cf3c5cebad.106.1 +3 -0
  18. runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069370.c4cf3c5cebad.106.0 +3 -0
  19. runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069624.c4cf3c5cebad.106.2 +3 -0
  20. test_results.json +8 -0
  21. trainer_state.json +163 -0
  22. training_args.bin +3 -0
.gitattributes CHANGED
@@ -1,35 +1,34 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
 
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ - video-classification
6
+ - videomae
7
+ - vision
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: videomae-base-finetuned-ucf101-subset
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # videomae-base-finetuned-ucf101-subset
19
+
20
+ This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3992
23
+ - Accuracy: 0.8645
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - training_steps: 148
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 2.1374 | 0.26 | 38 | 1.7413 | 0.5714 |
56
+ | 0.7949 | 1.26 | 76 | 0.7747 | 0.8 |
57
+ | 0.4279 | 2.26 | 114 | 0.4053 | 0.9143 |
58
+ | 0.291 | 3.23 | 148 | 0.3429 | 0.9286 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.24.0
64
+ - Pytorch 1.12.1+cu113
65
+ - Datasets 2.6.1
66
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.23,
3
+ "eval_accuracy": 0.864516129032258,
4
+ "eval_loss": 0.3992488980293274,
5
+ "eval_runtime": 13.7986,
6
+ "eval_samples_per_second": 11.233,
7
+ "eval_steps_per_second": 1.449
8
+ }
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MCG-NJU/videomae-base",
3
+ "architectures": [
4
+ "VideoMAEForVideoClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "decoder_hidden_size": 384,
8
+ "decoder_intermediate_size": 1536,
9
+ "decoder_num_attention_heads": 6,
10
+ "decoder_num_hidden_layers": 4,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "ApplyEyeMakeup",
16
+ "1": "ApplyLipstick",
17
+ "2": "Archery",
18
+ "3": "BabyCrawling",
19
+ "4": "BalanceBeam",
20
+ "5": "BandMarching",
21
+ "6": "BaseballPitch",
22
+ "7": "Basketball",
23
+ "8": "BasketballDunk",
24
+ "9": "BenchPress"
25
+ },
26
+ "image_size": 224,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "ApplyEyeMakeup": 0,
31
+ "ApplyLipstick": 1,
32
+ "Archery": 2,
33
+ "BabyCrawling": 3,
34
+ "BalanceBeam": 4,
35
+ "BandMarching": 5,
36
+ "BaseballPitch": 6,
37
+ "Basketball": 7,
38
+ "BasketballDunk": 8,
39
+ "BenchPress": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "model_type": "videomae",
43
+ "norm_pix_loss": true,
44
+ "num_attention_heads": 12,
45
+ "num_channels": 3,
46
+ "num_frames": 16,
47
+ "num_hidden_layers": 12,
48
+ "patch_size": 16,
49
+ "problem_type": "single_label_classification",
50
+ "qkv_bias": true,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.40.2",
53
+ "tubelet_size": 2,
54
+ "use_mean_pooling": false
55
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7436f538a6cfb972f90571579b5d43bb4826a298f7116f9adbc8a8e0a029e68c
3
+ size 344961984
preprocessor_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "videos",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_center_crop",
8
+ "crop_size",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "return_tensors",
15
+ "data_format",
16
+ "input_data_format"
17
+ ],
18
+ "crop_size": {
19
+ "height": 224,
20
+ "width": 224
21
+ },
22
+ "do_center_crop": true,
23
+ "do_normalize": true,
24
+ "do_rescale": true,
25
+ "do_resize": true,
26
+ "image_mean": [
27
+ 0.485,
28
+ 0.456,
29
+ 0.406
30
+ ],
31
+ "image_processor_type": "VideoMAEImageProcessor",
32
+ "image_std": [
33
+ 0.229,
34
+ 0.224,
35
+ 0.225
36
+ ],
37
+ "resample": 2,
38
+ "rescale_factor": 0.00392156862745098,
39
+ "size": {
40
+ "shortest_edge": 224
41
+ }
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf11598beab117b24348fef68b0fc8dfecc6baf2474bf3ea916650ec3e3ea33
3
+ size 134
runs/Nov09_01-44-16_588d19775fbb/1667958337.1126697/events.out.tfevents.1667958337.588d19775fbb.280.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527350f5f201b3afaf3986997b60c7b78e7c67c03a52be1885295b6732470e04
3
+ size 129
runs/Nov09_01-44-16_588d19775fbb/events.out.tfevents.1667958337.588d19775fbb.280.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816842d1069c34f9d4bfba291e3ad264e1895f873f33f611df5107594dcab8f4
3
+ size 129
runs/Nov09_01-44-16_588d19775fbb/events.out.tfevents.1667958570.588d19775fbb.280.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e5594d575ae1e5945491b0f804b3fa498cca2942288334a24f1cede6d7343b
3
+ size 128
runs/Nov10_07-25-30_8182e899e964/1668065304.7947109/events.out.tfevents.1668065304.8182e899e964.107.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9481d70989a578c5885a7987baa57dc56623255a38ce38b1189ab8d4fc6415
3
+ size 129
runs/Nov10_07-25-30_8182e899e964/events.out.tfevents.1668065304.8182e899e964.107.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa31273b9e6a9f50c600c37e35e57d1f936eda17633a57dccc191038276824fe
3
+ size 129
runs/Nov10_07-39-57_8182e899e964/1668066010.4314957/events.out.tfevents.1668066010.8182e899e964.742.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3a9c750251a293af3d4bbdca18ed4081137406d91f444513350d0e162a5dfa
3
+ size 129
runs/Nov10_07-39-57_8182e899e964/events.out.tfevents.1668066010.8182e899e964.742.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984cc5bae92303ee750774a97901d69de8d9284bc9c25576098ed79965866523
3
+ size 129
runs/Nov10_07-39-57_8182e899e964/events.out.tfevents.1668066300.8182e899e964.742.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faed7901f3d9ddee43285e018a5b9c396445bf928310623d79ad6d550240823a
3
+ size 128
runs/Nov10_08-33-15_c4cf3c5cebad/1668069370.6992447/events.out.tfevents.1668069370.c4cf3c5cebad.106.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7caa1d7011976eb1f91e6d888fb5c9623cb8405425da6b92042a365f97382d57
3
+ size 129
runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069370.c4cf3c5cebad.106.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2e9eb133f6ef9e106b9aa1cf7f084de1598d68492162976db3787d3d796ee9
3
+ size 129
runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069624.c4cf3c5cebad.106.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d325aa9387dd1d254ba2c2d35828f4207987ed326b510a0b1d9dee5e13a784c9
3
+ size 128
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.23,
3
+ "eval_accuracy": 0.864516129032258,
4
+ "eval_loss": 0.3992488980293274,
5
+ "eval_runtime": 13.7986,
6
+ "eval_samples_per_second": 11.233,
7
+ "eval_steps_per_second": 1.449
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9285714285714286,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
4
+ "epoch": 3.22972972972973,
5
+ "global_step": 148,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 3.3333333333333335e-05,
13
+ "loss": 2.3623,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 4.81203007518797e-05,
19
+ "loss": 2.2155,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.2,
24
+ "learning_rate": 4.43609022556391e-05,
25
+ "loss": 2.1374,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.26,
30
+ "eval_accuracy": 0.5714285714285714,
31
+ "eval_loss": 1.7412834167480469,
32
+ "eval_runtime": 6.1835,
33
+ "eval_samples_per_second": 11.32,
34
+ "eval_steps_per_second": 1.455,
35
+ "step": 38
36
+ },
37
+ {
38
+ "epoch": 1.01,
39
+ "learning_rate": 4.0601503759398494e-05,
40
+ "loss": 1.9183,
41
+ "step": 40
42
+ },
43
+ {
44
+ "epoch": 1.08,
45
+ "learning_rate": 3.6842105263157895e-05,
46
+ "loss": 1.4923,
47
+ "step": 50
48
+ },
49
+ {
50
+ "epoch": 1.15,
51
+ "learning_rate": 3.3082706766917295e-05,
52
+ "loss": 1.2149,
53
+ "step": 60
54
+ },
55
+ {
56
+ "epoch": 1.22,
57
+ "learning_rate": 2.9323308270676693e-05,
58
+ "loss": 0.7949,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.26,
63
+ "eval_accuracy": 0.8,
64
+ "eval_loss": 0.7746667265892029,
65
+ "eval_runtime": 6.3565,
66
+ "eval_samples_per_second": 11.012,
67
+ "eval_steps_per_second": 1.416,
68
+ "step": 76
69
+ },
70
+ {
71
+ "epoch": 2.03,
72
+ "learning_rate": 2.556390977443609e-05,
73
+ "loss": 0.8088,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 2.09,
78
+ "learning_rate": 2.1804511278195487e-05,
79
+ "loss": 0.535,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 2.16,
84
+ "learning_rate": 1.8045112781954888e-05,
85
+ "loss": 0.5405,
86
+ "step": 100
87
+ },
88
+ {
89
+ "epoch": 2.23,
90
+ "learning_rate": 1.4285714285714285e-05,
91
+ "loss": 0.4279,
92
+ "step": 110
93
+ },
94
+ {
95
+ "epoch": 2.26,
96
+ "eval_accuracy": 0.9142857142857143,
97
+ "eval_loss": 0.4053409993648529,
98
+ "eval_runtime": 6.2263,
99
+ "eval_samples_per_second": 11.243,
100
+ "eval_steps_per_second": 1.445,
101
+ "step": 114
102
+ },
103
+ {
104
+ "epoch": 3.04,
105
+ "learning_rate": 1.0526315789473684e-05,
106
+ "loss": 0.3461,
107
+ "step": 120
108
+ },
109
+ {
110
+ "epoch": 3.11,
111
+ "learning_rate": 6.766917293233083e-06,
112
+ "loss": 0.2509,
113
+ "step": 130
114
+ },
115
+ {
116
+ "epoch": 3.18,
117
+ "learning_rate": 3.007518796992481e-06,
118
+ "loss": 0.291,
119
+ "step": 140
120
+ },
121
+ {
122
+ "epoch": 3.23,
123
+ "eval_accuracy": 0.9285714285714286,
124
+ "eval_loss": 0.3428815007209778,
125
+ "eval_runtime": 6.583,
126
+ "eval_samples_per_second": 10.633,
127
+ "eval_steps_per_second": 1.367,
128
+ "step": 148
129
+ },
130
+ {
131
+ "epoch": 3.23,
132
+ "step": 148,
133
+ "total_flos": 1.460491890402263e+18,
134
+ "train_loss": 1.0492687128685616,
135
+ "train_runtime": 239.2161,
136
+ "train_samples_per_second": 4.949,
137
+ "train_steps_per_second": 0.619
138
+ },
139
+ {
140
+ "epoch": 3.23,
141
+ "eval_accuracy": 0.864516129032258,
142
+ "eval_loss": 0.3992488980293274,
143
+ "eval_runtime": 14.1288,
144
+ "eval_samples_per_second": 10.971,
145
+ "eval_steps_per_second": 1.416,
146
+ "step": 148
147
+ },
148
+ {
149
+ "epoch": 3.23,
150
+ "eval_accuracy": 0.864516129032258,
151
+ "eval_loss": 0.3992488980293274,
152
+ "eval_runtime": 13.7986,
153
+ "eval_samples_per_second": 11.233,
154
+ "eval_steps_per_second": 1.449,
155
+ "step": 148
156
+ }
157
+ ],
158
+ "max_steps": 148,
159
+ "num_train_epochs": 9223372036854775807,
160
+ "total_flos": 1.460491890402263e+18,
161
+ "trial_name": null,
162
+ "trial_params": null
163
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:792e5bbb6401737310ce85268dbb59b0341ba0f460f141677841cd0a9dc136f9
3
+ size 4603